Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering.
Lists
Only you see this
Abstract
Models for computer vision are commonly defined either w.r.t. low-level concepts such as pixels that are to be grouped, or w.r.t. high-level concepts such as semantic objects that are to be detected and tracked. Combining bottom-up grouping with top-down detection and tracking, although highly desirable, is a challenging problem. We state this joint problem as a co-clustering problem that is principled and tractable by existing algorithms. We demonstrate the effectiveness of this approach by combining bottom-up motion segmentation by grouping of point trajectories with high-level multiple object tracking by clustering of bounding boxes. We show that solving the joint problem is beneficial at the low-level, in terms of the FBMS59 motion segmentation benchmark, and at the high-level, in terms of the Multiple Object Tracking benchmarks MOT15, MOT16, and the MOT17 challenge, and is state-of-the-art in some metrics.
BibTeX
@article{keuper2020motion,
author = {Margret Keuper and Siyu Tang and Bjoern Andres and Thomas Brox and Bernt Schiele},
title = {{Motion Segmentation \& Multiple Object Tracking by Correlation Co-Clustering.}},
journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
year = {2020},
url = {https://openreview.net/forum?id=92cinRz0Yex},
}Loading related content...